# Parameters
data_name = "wES;FaceP;E14.5;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
tomtom_report_root = "http://mitra.stanford.edu/kundaje/msharmin/report/tomtom_outs/cells"
task_dir = "task_260-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_260-naivegw/NaiveauPRC.txt"
homer_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_scans"
reportfile = "/mnt/lab_data/kundaje/msharmin/annotations/filtering samples_MS2.xlsx"
sheetname = "filter23"

from matlas.reports import display_metadata

load data from labcluster

Using TensorFlow backend.
2019-08-30 19:38:57,634 [WARNING] git-lfs not installed

display_metadata(data_name, perf_file, reportfile, sheetname)

from matlas.reports import display_paiwise_pattern_comparison
from matlas.reports import display_denovo_patterns

display_denovo_patterns(data_name, modisco_root=modisco_root)

TF-MoDISco is using the TensorFlow backend.

display_paiwise_pattern_comparison(data_name, modisco_root, homer_root)

MetaData Name	Description
Cell type	embryonic facial prominence(e14.5)
Cell Group	ES cells and embryonic tissues
Experiment Name	DHS
Experiment Group	ENCODE

replicate	Naïve overlap peaks	IDR peaks	TSS enrichment (< 8 is very poor <10 is low)	Final number of unique mapping, dup-filtered, chrM filtered reads	Number of reads in called peak regions	Fraction of reads in called peak regions	Number of reads in promoter regions	Fraction of reads in promoter regions	Number of reads in enhancer regions	Fraction of reads in enhancer regions
rep1	368276	228990	9.0167	159460017	NA	NA	NA	NA	NA	NA
rep2	260944	166121	13.0191	85916743	16947028	0.1973	9509304	0.1107	38272924	0.4456

Metric	Value
auPRC	0.6297
Calibrated Recall at 50% FDR	0.226
Number of Positive Examples in Test Data	171709
Number of Negative Examples in Test Data	7899142
Imbalance Ratio in Test Data	0.0213
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2452 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 1743 SequenceContrib ScoresHyp_Contrib Scores	Twist1, Olig2, Tal1, Myog, Tcf3, Ptf1a, Ascl2, Tcf21, Myf5, Lyl1, Myf6, Atoh1, Msc, Neurod1, Ascl1, Bhlha15, Neurod2, Myod1, Tfap4, Figla, Tcf4, Tcf12, Tgif1
metacluster_0/pattern_2 # seqlets: 1739 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp4, Klf3, Sp1, Klf7, E2f4, Klf4, Klf6, Klf8, Klf12, Klf1, Egr1, Zbtb17, Egr2, E2f1, Klf5, Zfp281, Zfp740, Zfx, Sp5, Zbtb1, Egr3
metacluster_0/pattern_3 # seqlets: 1557 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_4 # seqlets: 1521 SequenceContrib ScoresHyp_Contrib Scores	Nfic
metacluster_0/pattern_5 # seqlets: 1332 SequenceContrib ScoresHyp_Contrib Scores	Maz, Wt1, Klf15, Sall4, Rela, Bcl6, Srebf2, Zic1
metacluster_0/pattern_6 # seqlets: 1057 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib
metacluster_0/pattern_7 # seqlets: 829 SequenceContrib ScoresHyp_Contrib Scores	Pax6, Uncx, Lhx4, Lhx8, Lhx3, Hoxc6, Esx1, Lhx2, Meox2, Phox2b, Vsx2, Sebox, Alx1, En2, Prop1, Otp, Prrx2, Pou1f1, Prrx1, Alx3, Dbx1, Dlx5, Gbx2, En1, Hoxa2, Phox2a, Gbx1, Shox2, Arid3b, Hoxc9, Lhx6, Arx, Lhx5, Hoxd3, Dlx3, Rhox6, Lhx9, Tlx2, Dlx2, Vsx1, Lmx1b, Gsx2, Dlx1, Hoxa1, Alx4, Lhx1, Rax, Dbx2, Nkx6-1, Dlx4, Isx, Nobox, Pou2f2, Meox1, Emx2, Mnx1, Msx1, Lbx2, Msx2, Hoxd1, Nkx6-3, Pou3f1, Pou2f1, Pax7, Pax4, Evx1, Sp7, Msx3, Noto, Evx2, Lmx1a, Pou3f2, Hnf1b, Hnf1a, Pou3f4, Vax2, Hoxa4, Vax1, Hoxc5, Pou2f3, Nkx1-2, Pou4f3, Hoxa3, Hoxa7, Hoxa5, Nkx1-1, Hoxa6, Arid3a, Pdx1
metacluster_0/pattern_8 # seqlets: 708 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_9 # seqlets: 705 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Jdp2, Creb5, Creb1, Crem, Atf1, Nfil3, Jun, Cebpb, Cebpa, Dbp, Atf3, Tef, Hlf, Mafb, Srebf1, Ddit3, Fosl1, Fosl2, Mlx, Atf4, Jund, Cebpd, Tfec, Gmeb2, Esr2, Cebpg, Rxrb
metacluster_0/pattern_10 # seqlets: 633 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_11 # seqlets: 611 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_12 # seqlets: 608 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_13 # seqlets: 583 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Fli1, Erg, Elk4, Ets1, Elk3, Etv6, XP_911724.4, Etv5, Etv3, Etv1, Etv4, Etv2, Elf4, Elf1, Elf2, Ehf, Elf5, Fev, Spi1, Spdef, Spib, Elf3, Spic, Irf4, Irf8
metacluster_0/pattern_14 # seqlets: 539 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_0/pattern_15 # seqlets: 518 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_16 # seqlets: 486 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_17 # seqlets: 460 SequenceContrib ScoresHyp_Contrib Scores	Fos, Batf, Fosb, Junb, Bach2, Nfe2l2, Bach1, Nfe2, Mafk, Mafa
metacluster_0/pattern_18 # seqlets: 391 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox10, Sox3, Sox2, Sox4, Sox6, Sox17
metacluster_0/pattern_19 # seqlets: 312 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_0/pattern_20 # seqlets: 277 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfeb, Arntl, Usf2, Tfe3, Mitf, Bhlhe40, Clock, Arnt, Npas2, Tcfl5, Creb3l2, Bhlhe41, Xbp1
metacluster_0/pattern_21 # seqlets: 250 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_0/pattern_22 # seqlets: 197 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_0/pattern_23 # seqlets: 137 SequenceContrib ScoresHyp_Contrib Scores	Foxd3, Foxj3, Gm5294, Foxd1, Foxj2, Foxc1, Foxc2, Foxj1, Foxa1, Foxp2, Foxo3, Foxa2, Foxa3, Foxk1, Foxb1, Foxl1, Foxo4, Foxl2, Foxp1, Foxg1, Foxq1, Foxm1, Foxo1, Sry
metacluster_0/pattern_24 # seqlets: 136 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_25 # seqlets: 131 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_26 # seqlets: 103 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_0/pattern_27 # seqlets: 67 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_28 # seqlets: 56 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_29 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores